Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/CodeAbra/iai-personal-memory-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/codeabra/iai-personal-memory-engine/iai-directive)<a href="https://agentmods.dev/commands/codeabra/iai-personal-memory-engine/iai-directive"><img src="https://agentmods.dev/badge/commands/codeabra/iai-personal-memory-engine/iai-directive.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00121 |
| Opus 5 | $0.00009 | $0.00060 |
| Sonnet 5 | $0.00004 | $0.00024 |
| Haiku 4.5 | $0.00002 | $0.00012 |
Grade A, and why
iai-directive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the following command exactly, substituting the user's typed rule for
$ARGUMENTS, and report its output:
iai capture --directive "$ARGUMENTS"
This is a thin wrapper over the CLI mechanism itself -- it adds no privilege the CLI does not already grant. Do not paraphrase or summarize the user's text before passing it; forward it verbatim as the quoted argument.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 18 lines · 18 tokens per session scan A 422aaf8c687e
iai-directive is a command published in the GitHub repository CodeAbra/iai-personal-memory-engine (855 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 121 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other commands, from other repositories
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
dreaming
Configure and run the dreaming subsystem that consolidates, combines, and prunes memories on a wall-clock floor. Invoke when the user asks to turn dreaming on/off, change how often it runs, run a one-shot dreaming pass, or check when dreaming last fired. Defaults: mode=auto, interval=30m for auto / 24h for on, include…
reset_project
Wipe the per-project memory cache for the active project when it was re-cloned from the same path.
advisor
Run the advisor reflection over the active project (anchored recommendations, no remote calls).
list_memories
List the kimi-memory entries for the current project.
reason
Think through a question using memory-backed retrieval.